Table Transformer做表格检测和识别实践

news2024/11/17 0:04:39

计算机视觉方面的三大顶级会议：ICCV,CVPR,ECCV.统称ICE
CVPR 2022文档图像分析与识别相关论文26篇汇集简介

论文： PubTables-1M: Towards comprehensive table extraction from unstructured documents是发表于CVPR上的一篇论文
作者发布了两个模型，表格检测和表格结构识别。

论文讲解可以参考【论文阅读】PubTables- 1M: Towards comprehensive table extraction from unstructured documents

在这里插入图片描述

hugging face Table Transformer 使用文档
hugging face Table DETR 使用文档

检测表格

from huggingface_hub import hf_hub_download
from transformers import AutoImageProcessor, TableTransformerForObjectDetection
import torch
from PIL import Image

file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png")

 
image = Image.open(file_path).convert("RGB")

 

image_processor = AutoImageProcessor.from_pretrained("microsoft/table-transformer-detection")
model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-detection")

inputs = image_processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to COCO API
target_sizes = torch.tensor([image.size[::-1]])
results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[
    0
]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
        f"Detected {model.config.id2label[label.item()]} with confidence "
        f"{round(score.item(), 3)} at location {box}"
    )
 
    region = image.crop(box) #检测
    region.save('xxx.jpg') #保存

# Detected table with confidence 1.0 at location [202.1, 210.59, 1119.22, 385.09]

在这里插入图片描述

结果：效果不错

表格结构识别

参考：https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Table%20Transformer/Using_Table_Transformer_for_table_detection_and_table_structure_recognition.ipynb



import torch
from PIL import Image
from transformers import DetrFeatureExtractor
from transformers import AutoImageProcessor, TableTransformerForObjectDetection
from huggingface_hub import hf_hub_download



feature_extractor = DetrFeatureExtractor()

file_path = hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png")
image = Image.open(file_path).convert("RGB")

encoding = feature_extractor(image, return_tensors="pt")
model = TableTransformerForObjectDetection.from_pretrained("microsoft/table-transformer-structure-recognition")


with torch.no_grad():
    outputs = model(**encoding)
target_sizes = [image.size[::-1]]
results = feature_extractor.post_process_object_detection(outputs, threshold=0.6, target_sizes=target_sizes)[0]
# plot_results(image, results['scores'], results['labels'], results['boxes'])
results

在这里插入图片描述

其他：
获取列图像:

columns_box_list = [results['boxes'][i].tolist() for i in range(len(results['boxes'])) if results['labels'][i].item()==1] 


columns_1 = image.crop(columns_box_list[0]) 
columns_1.save('columns_1.jpg') #保存

在这里插入图片描述

可视化：

import matplotlib.pyplot as plt
# colors for visualization
COLORS = [[0.000, 0.447, 0.741], [0.850, 0.325, 0.098], [0.929, 0.694, 0.125],
          [0.494, 0.184, 0.556], [0.466, 0.674, 0.188], [0.301, 0.745, 0.933]]


def plot_results(pil_img, scores, labels, boxes):
    plt.figure(figsize=(16, 10))
    plt.imshow(pil_img)
    ax = plt.gca()
    colors = COLORS * 100
    for score, label, (xmin, ymin, xmax, ymax), c in zip(scores.tolist(), labels.tolist(), boxes.tolist(), colors):
        ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin,
                                   fill=False, color=c, linewidth=3))
        text = f'{model.config.id2label[label]}: {score:0.2f}'
        ax.text(xmin, ymin, text, fontsize=15,
                bbox=dict(facecolor='yellow', alpha=0.5))
    plt.axis('off')
    plt.show()

post_process_object_detection方法：

OpenCV PIL图像格式互转

参考：https://blog.csdn.net/dcrmg/article/details/78147219

PIL–》OpenCV

cv2.cvtColor(numpy.asarray(image),cv2.COLOR_RGB2BGR)

import cv2
from PIL import Image
import numpy
 
image = Image.open("plane.jpg")
image.show()
img = cv2.cvtColor(numpy.asarray(image),cv2.COLOR_RGB2BGR)
cv2.imshow("OpenCV",img)
cv2.waitKey()

OpenCV --》 PIL

 Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))

import cv2
from PIL import Image
import numpy
 
img = cv2.imread("plane.jpg")
cv2.imshow("OpenCV",img)
image = Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))
image.show()
cv2.waitKey()